A Three-Step Process for Large-Scale Cloud Services

Minutes matter for trauma patients in hemorrhagic shock. How trauma team function impacts time to the next phase of care has not been rigorously evaluated. We hypothesized better team performance scores to be associated with decreased time to the next phase of trauma care. This retrospective secondary analysis of a prospective multicenter observational study included hypotensive trauma patients at 19 centers. Using trauma video review, we analyzed team performance with the validated Non-Technical Skills for Trauma scale: leadership, cooperation and resource management, communication, assessment/decision making, and situational awareness. The primary outcome was minutes from patient arrival to next phase of care; deaths in the bay were excluded. Secondary outcomes included time to initiation and completion of first unit of blood and inpatient mortality. Associations between team dynamics and outcomes were assessed with a linear mixed-effects model adjusting for Injury Severity Score, mechanism, initial blood pressure and heart rate, number of team members, and trauma team lead training level and sex. A total of 441 patients were included. The median Injury Severity Score was 22 (interquartile range, 10-34), and most (61%) sustained blunt trauma. The median time to next phase of care was 23.5 minutes (interquartile range, 17-35 minutes). Better leadership, communication, assessment/decision making, and situational awareness scores were associated with faster times to next phase of care (all p < 0.05). Each 1-point worsening in the Non-Technical Skills for Trauma scale score (scale, 5-15) was associated with 1.6 minutes more in the bay. The median resuscitation team size was 12 (interquartile range, 10-15), and larger teams were slower ( p < 0.05). Better situational awareness was associated with faster completion of first unit of blood by 4 to 5 minutes ( p < 0.05). Better team performance is associated with faster transitions to next phase of care in hypotensive trauma patients, and larger teams are slower. Trauma team training should focus on optimizing team performance to facilitate faster hemorrhage control. Therapeutic/Care Management; Level III.

Cloud computing and storage have attracted a lot of attention due to the ever increasing demand for reliable and cost-effective access to vast resources and services available on the Internet. Cloud services are typically hosted in a set of geographically distributed data centers, which we will call the cloud infrastructure. To minimize the total cost of ownership of this cloud infrastructure (which accounts for both the upfront capital cost and the operational cost of the infrastructure resources), the infrastructure owners/operators must do a careful planning of data center locations in the targeted service area (for example the US territories), data center capacity provisioning (i.e., the total CPU cycles per second that can be provided in each data center). In addition, they must have flow control policies that will distribute the incoming user requests to the available resources in the cloud infrastructure. This paper presents an approach for solving the unified problem of data center placement and provisioning, and request flow control in one shot. The solution technique is based on mathematical programming. Experimental results, using Google cluster data and placement/provisioning of up to eight data center sites demonstrate the cost savings of the proposed problem formulation and solution approach.

Cloud platforms deploy data centers geographically distributed around the world and application providers select cloud infrastructures based on the requirements of their applications. While existing works mostly focus on the comparison on cloud services, we argue that proximity also plays a very important role when deciding in which cloud infrastructures to deploy the applications. In this paper, we design and evaluate the system, we call CSS, for automatic selection of cloud infrastructures. It not only considers the deployment cost, but also takes into account the location of cloud infrastructures, application clients and related applications, and the interaction among application components when selecting the cloud infrastructures. In order to address the scalability issue when the number of data centers and application components is large, we propose a stepwise application placement algorithm. Through experiments, we show that the algorithm is able to find a near-optimal placement policy within very short period of time.

Cloud computing is provisioned with high flexibility with regard to on demand infrastructures, platforms and software as services through the Internet. The unique characteristics of cloud services such as dynamic and diverse services offering at different levels, as well as the lack of standardized description, are becoming important challenges in efficiently discovering cloud services for customers. In this paper, we propose a cloud service search engine that has the capability to automatically identify cloud services aiming at improving the accuracy when searching cloud services in real environments. Our search engine can detect cloud services effectively from the Web sources. Furthermore, we focus on learning the cloud service features, such as similarity function, semantic ontology and cloud service components to identify the cloud services. We use a real cloud service dataset to build an identifier. Our cloud service identifier can be used to automatically determine whether a given Web source is a cloud service with high accuracy.

Cloud technologies quickly evolve and require efficient ways to process and deploy data for high operational performance and low cost. This study looks at code-driven automation applied to cloud infrastructure, with a focus on Terraform, Jenkins, and Kubernetes. Automating infrastructure provisioning and application deployments, these tools minimize human intervention and potential human error, thus optimizing operational effectiveness. The findings indicate that code-driven automation not only accelerates deployments but also provides scalability and dependability among many cloud environments, thus ensuring fast and efficient delivery of cloud services. With this strategy, organizations can optimize their cloud operations and resource utilization needs. The research helps to understand how effective automation of processes would improve cloud infrastructure management and service delivery in very dynamic technological times. Keywords—Cloud Infrastructure Management, Code-Driven Automation, Infrastructure as Code (IaC), Automated Deployment, Cloud Efficiency, Resource Utilization, CI/CD Pipelines, Kubernetes.

The paper presents the development of the private cloud infrastructure providing advanced services for research in mechanical and medical engineering. The cloud services have been developed by using Apache jclouds API and JetS3t Toolkit to enhance management of Eucalyptus cloud infrastructure and to increase accessibility of engineering software. The performance of the developed cloud infrastructure has been assessed testing CPU, memory IO, disk IO, network and the deployed software services. The obtained results have been compared with the performance of the native hardware. The technical implementation of deployed cloud services has been evaluated by the utilising a number of use cases from different research areas of mechanical and medical engineering.DOI: http://dx.doi.org/10.5755/j01.itc.44.3.7379

Scheduling large-scale and resource-intensive workflows in cloud infrastructure is one of the main challenges for cloud service providers (CSPs). Cloud infrastructure is more efficient when virtual machines and other resources work up to their full potential. The main factor that influences the quality of cloud services is the distribution of workflow on virtual machines (VMs). Scheduling tasks to VMs depends on the type of workflow and mechanism of resource allocation. Scientific workflows include large-scale data transfer and consume intensive resources of cloud infrastructures. Therefore, scheduling of tasks from scientific workflows on VMs requires efficient and optimized workflow scheduling techniques. This paper proposes an optimised workflow scheduling approach that aims to improve the utilization of cloud resources without increasing execution time and execution cost.

The advent of cloud computing has made access to computing infrastructure available to millions of users that face resource constraints. In the context of high performance computing (HPC), public cloud resources have emerged as a cost‐effective alternative to expensive on‐premises clusters. However, there are several challenges and limitations in adopting this approach. This paper proposes HPC@Cloud , a provider‐agnostic open‐source software toolkit that facilitates the migration, testing, and execution of HPC applications in public clouds. The toolkit takes advantage of various fault tolerance technologies to enable the use of inexpensive transient cloud infrastructure, commonly known as “spot” instances. Also, it features integration with singularity containers, allowing users to run complex applications on virtual HPC clusters in a portable and reproducible way. Finally, it provides a data‐based empirical approach to estimating cloud infrastructure costs for HPC workloads. The results obtained on two public cloud providers (AWS and Vultr) show that: (i) HPC@Cloud can efficiently build virtual HPC clusters on the cloud; (ii) the new adaptive fault tolerance strategy outperforms other existing strategies based on blocking restoration; (iii) the integration of singularity containers into HPC@Cloud improves the portability of HPC applications to public clouds with negligible performance penalty to the applications; (iv) the proposed cost prediction approach can estimate the cost of running the applications on AWS and Vultr with up to 93% accuracy on average.

The emergence of new capabilities such as virtualization and elastic (private or public) cloud computing infrastructures has made it possible to deploy multiple applications, on demand, on the same cloud infrastructure. A major challenge to achieve this possibility, however, is that modern applications are typically distributed, structured systems that include not only computational and storage entities, but also policy entities (e.g., load balancers, firewalls, intrusion prevention boxes). Deploying applications on a cloud infrastructure without the policy entities may introduce substantial policy violations and/or security holes. In this paper, we present PACE: the first systematic framework for Policy-Aware Application Cloud Embedding. We precisely define the policy-aware, cloud application embedding problem, study its complexity and introduce simple, efficient, online primal-dual algorithms to embed applications in cloud data centers. We conduct evaluations using data from a real, large campus network and a realistic data center topology to evaluate the feasibility and performance of PACE. We show that deployment in a cloud without considering in-network policies may lead to a large number of policy violations (e.g., using tree routing as a way to enforce in-network policies may observe up to 91% policy violations). We also show that our embedding algorithms are very efficient by comparing with a good online fractional embedding algorithm.

The proliferation of big data and analytic workloads has driven the need for cloud compute and cluster-based job processing. With Apache Spark, users can process terabytes of data at ease with hundreds of parallel executors. Providing low latency access to Spark clusters and sessions is a challenging problem due to the large overheads of cluster creation and session startup. In this paper, we introduce Intelligent Pooling, a system for proactively provisioning compute resources to combat the aforementioned overheads. Our system (1) predicts usage patterns using an innovative hybrid Machine Learning (ML) model with low latency and high accuracy; and (2) optimizes the pool size dynamically to meet customer demand while reducing extraneous COGS. The proposed system auto-tunes its hyper-parameters to balance between performance and operational cost with minimal to no engineering input. Evaluated using large-scale production data, Intelligent Pooling achieves up to 43% reduction in cluster idle time compared to static pooling when targeting 99% pool hit rate. Currently deployed in production, Intelligent Pooling is on track to save tens of million dollars in COGS per year as compared to traditional pre-provisioned pools.

Significance This, coupled with interdependencies among cloud services and growing sophistication of cyber criminals, is driving improvement in the operational resiliency of cloud services. While cloud computing at present is more reliable than not, the fact that cloud outages with a global impact still occur about a dozen times each year exposes continuing gaps, even among top providers. Impacts The black market for cybercrime related to cloud services will proliferate. A targeted attack against cloud infrastructure by a state-linked cyber actor would cause wide-ranging disruption. Large cloud services providers are likely to dominate the global market since they can lower costs while financing innovation.

With the growing popularity of the service oriented computing paradigm, reliable cloud service delivery has assumed prime importance. This, in turn, demands appropriate techniques for reliability assessment of cloud services. In this paper, we present a model for reliability assessment of cloud services in a smart city infrastructure hosted as cloud service. Subsequently we provide the detailed methodology for obtaining cloud services reliability using Markov Model, Graph Theory and Queuing Theory. It has been assumed that critical infrastructures of a smart city including energy, water, gas, transportation, public health and safety, irrigation, communication networks are provided as services hosted on cloud infrastructures.

This article describes how with the rapid growth of cloud services in recent years, it is very difficult to choose the most suitable cloud services among those services that provide similar functionality. The quality of services (QoS) is considered the most significant factor for appropriate service selection and user satisfaction in cloud computing. However, with a vast diversity in the cloud services, selection of a suitable cloud service is a very challenging task for a customer under an unpredictable environment. Due to the multidimensional attributes of QoS, cloud service selection problems are treated as a multiple criteria decision-making (MCDM) problem. This study introduces a methodology for determining the appropriate cloud service by integrating the AHP weighing method with TOPSIS method. Using AHP, the authors define the architecture for selection process of cloud services and compute the criteria weights using pairwise comparison. Thereafter, with the TOPSIS method, the authors obtain the final ranking of the cloud service based on overall performance. A real-time cloud case study affirms the potential of our proposed methodology, when compared to other MCDM methods. Finally, a sensitivity analysis testifies the effectiveness and the robustness of our proposed methodology.

This paper discusses preliminary stages and key research challenges tackled by TEOS (experiments) in the EC funded BonFIRE project. TEOS experiments aim to determine the conditions for achieving resilient and optimal service compositions for very large scale service composition scenarios relating to Future Internet applications. We deploy and test two large scale service optimization models under different scenarios and configurations on the multi-site cloud infrastructure established by the EC BonFIRE initiative. The outcome of TEOS will not only verify the feasibility of the optimization models in dealing with large number of services and future-internet scenarios but also the nature and design of our experiments will help in evaluating the underlying BonFIRE infrastructure.

The cloud infrastructure provider (CIP) in a cloud computing platform must provide security and isolation guarantees to a service provider (SP), who builds the service(s) for such a platform. We identify last level cache (LLC) sharing as one of the impediments to finer grain isolation required by a service, and advocate two resource management approaches to provide performance and security isolation in the shared cloud infrastructure - cache hierarchy aware core assignment and page coloring based cache partitioning. Experimental results demonstrate that these approaches are effective in isolating cache interference impacts a VM may have on another VM. We also incorporate these approaches in the resource management (RM) framework of our example cloud infrastructure, which enables the deployment of VMs with isolation enhanced SLAs.